The cryptocurrency market is highly volatile compared to traditional financial markets. Hence, forecasting its volatility is crucial for risk management. In this paper, we investigate CryptoQuant data (e.g. on-chain analytics, exchange and miner data) and whale-alert tweets, and explore their relationship to Bitcoin's next-day volatility, with a focus on extreme volatility spikes. We propose a deep learning Synthesizer Transformer model for forecasting volatility. Our results show that the model outperforms existing state-of-the-art models when forecasting extreme volatility spikes for Bitcoin using CryptoQuant data as well as whale-alert tweets. We analysed our model with the Captum XAI library to investigate which features are most important. We also backtested our prediction results with different baseline trading strategies and the results show that we are able to minimize drawdown while keeping steady profits. Our findings underscore that the proposed method is a useful tool for forecasting extreme volatility movements in the Bitcoin market.
Blockchain finance has become a part of the world financial system, most typically manifested in the attention to the price of Bitcoin. However, a great deal of work is still limited to using technical indicators to capture Bitcoin price fluctuation, with little consideration of historical relationships and interactions between related cryptocurrencies. In this work, we propose a generic Cross-Cryptocurrency Relationship Mining module, named C2RM, which can effectively capture the synchronous and asynchronous impact factors between Bitcoin and related Altcoins. Specifically, we utilize the Dynamic Time Warping algorithm to extract the lead-lag relationship, yielding Lead-lag Variance Kernel, which will be used for aggregating the information of Altcoins to form relational impact factors. Comprehensive experimental results demonstrate that our C2RM can help existing price prediction methods achieve significant performance improvement, suggesting the effectiveness of Cross-Cryptocurrency interactions on benefitting Bitcoin price prediction.
Non-Fungible Tokens (NFTs) are a relatively unexplored class of assets. Designing strategies to forecast NFT trends is an intricate task due to its extremely volatile nature. The market is largely driven by public sentiment and "hype", which in turn has a high correlation with conversations taking place on social media platforms like Twitter. Prior work done for modelling stock market data does not take into account the extent of impact certain highly influential tweets and their authors can have on the market. Building on these limitations and the nature of the NFT market, we propose a novel reach-aware temporal learning approach to make predictions for forecasting future trends in the NFT market. We perform experiments on a new dataset consisting of over 1.3 million tweets and 180 thousand NFT transactions spanning over 15 NFT collections curated by us. Our model (TA-NFT) outperforms other state-of-the-art methods by an average of 36%. Through extensive quantitative and ablative analysis, we demonstrate the ability of our approach as a practical method for predicting NFT trends.
Digital currency is considered a form of currency which is used in the digital world such as digital forms or electronic devices. Several terms are synonyms for digital currency like digital money, electronic money, and cyber cash. Accurate prediction of the digital currency is an urgent necessity due to its impacts on the economic community. The electronic economy is very dangerous and must be approached with great caution, so as to avoid or minimize the risks that occur in such cases. Deep neural network (DNN) algorithm was improved to predict the Bitcoin price and then achieve the main goal of reducing financial risks to proceed with electronic business, and good estimation was achieved by using informative data such as transactions and currency return. The proposed method extracted features of related Bitcoin and used the informative ones. Transaction plan considered building nodes in terms of network. Development of deep learning algorithms opens the horizons for the development of electronic businesses that use digital currency. The proposed method achieved worthy results in terms of accuracy (53.4%) and correct prediction (MSE 1.02) and offers the prospect of other research in this area.
Shaimaa Alghamdi, Sara Alqethami, Tahani Alsubait, Hosam Alhakami
In recent years, many investors have used cryptocurrencies, prompting specialists to find out the factors that affect cryptocurrencies’ prices. Therefore, one of the most popular methods that have been used to predict cryptocurrency prices is sentiment analysis. It is a widespread technique utilized by many researchers on social media platforms, particularly on Twitter. Thus, to determine the relationship between investors’ sentiment and the volatility of cryptocurrency prices, this study forecasts the cryptocurrency prices using the Long-Term-Short-Memory (LSTM) deep learning algorithm. In addition, Twitter users’ sentiments using Support Vector Machine (SVM) and Naive Bayes (NB) machine learning approaches are analyzed. As a result, in the classification of the bitcoin (BTC) and Ethereum (ETH) datasets of investors’ sentiments into (Positive, Negative, and Neutral), the SVM algorithm outperformed the NB algorithm with an accuracy of 93.95% and 95.59%, respectively. Furthermore, the forecasting regression model achieves an error rate of 0.2545 for MAE, 0.2528 for MSE, and 0.5028 for RMSE.
Aspiring to achieve an accurate Bitcoin price prediction based on people's opinions on Twitter usually requires millions of tweets, using different text mining techniques (preprocessing, tokenization, stemming, stop word removal), and developing a machine learning model to perform the prediction. These attempts lead to the employment of a significant amount of computer power, central processing unit (CPU) utilization, random-access memory (RAM) usage, and time. To address this issue, in this paper, we consider a classification of tweet attributes that effects on price changes and computer resource usage levels while obtaining an accurate price prediction. To classify tweet attributes having a high effect on price movement, we collect all Bitcoin-related tweets posted in a certain period and divide them into four categories based on the following tweet attributes: $(i)$ the number of followers of the tweet poster, $(ii)$ the number of comments on the tweet, $(iii)$ the number of likes, and $(iv)$ the number of retweets. We separately train and test by using the Q-learning model with the above four categorized sets of tweets and find the best accurate prediction among them. Especially, we design several reward functions to improve the prediction accuracy of the Q-leaning. We compare our approach with a classic approach where all Bitcoin-related tweets are used as input data for the model, by analyzing the CPU workloads, RAM usage, memory, time, and prediction accuracy. The results show that tweets posted by users with the most followers have the most influence on a future price, and their utilization leads to spending 80\% less time, 88.8\% less CPU consumption, and 12.5\% more accurate predictions compared with the classic approach.
Cryptocurrency is one of the famous financial state in all over the world which cause several type of risks that effect on the intrinsic assessment of risk auditors. From the beginning the growth of cryptocurrency gives the financial business with the wide risk in term of presentation of money laundering. In the institution of financial supports such as anti-money laundering, banks and secrecy of banks proceed as a specialist of risk, manager of bank and officer of compliance which has a provocation for the related transaction through cryptocurrency and the users who hide the illegal funds.In this study, the Hierarchical Risk Parity and unsupervised machine learning applied on the cryptocurrency framework. The process of professional accounting in term of inherent risk connected with cryptocurrency regarding the occurrence likelihood and statement of financial impact. Determining cryptocurrency risks comprehended to have a high rate of occurrence likelihood and the access of private key which is unauthorized. The professional cryptocurrency experience in transaction cause the lower risk comparing the less experienced one. The Hierarchical Risk Parity gives the better output in term of returning the adjusted risk tail to get the better risk management result.The result section shows the proposed model is robust to various intervals which are re-balanced and the co-variance window estimation.
Cryptocurrencies are peer-to-peer-based transaction systems where the data exchanges are secured using the secure hash algorithm (SHA)-256 and message digest (MD)-5 algorithms. The prices of cryptocurrencies are highly volatile and follow stochastic moments and have reached their unpredictable limits. They are commonly used for investment and have become a substitute for other types of investment like metals, estates, and the stock market. Their importance in the market raises the strict requirement for a sturdy forecasting model. However, cryptocurrency price prediction is quite challenging due to its dependency on other cryptocurrencies. Many researchers have used machine learning and deep learning models, and other market sentiment-based models to predict the price of cryptocurrencies. As all the cryptocurrencies belong to a specific class, we can infer that the increase in the price of one cryptocurrency can lead to a price change for other cryptocurrencies. Researchers had also utilized the sentiments from tweets and other social media platforms to increase the performance of their proposed system. Motivated by these, in this paper, we propose a hybrid and robust framework,DL-Gues, for cryptocurrency price prediction, that considers its interdependency on other cryptocurrencies and also on market sentiments. We have considered price prediction ofDashcarried out using price history and tweets ofDash,Litecoin, andBitcoinfor various loss functions for validation. Further, to check the usability ofDL-GuesSon other cryptocurrencies, we have also inferred results for price prediction ofBitcoin-Cashwith the price history and tweets ofBitcoin-Cash,Litecoin, andBitcoin.
Bitcoin has grown in popularity and has now attracted the attention of individual and institutional investors. Accurate Bitcoin price direction forecasts are important for determining the trend in Bitcoin prices and asset allocation. This paper addresses several unanswered questions. How important are business cycle variables like interest rates, inflation, and market volatility for forecasting Bitcoin prices? Does the importance of these variables change across time? Are the most important macroeconomic variables for forecasting Bitcoin prices the same as those for gold prices? To answer these questions, we utilize tree-based machine learning classifiers, along with traditional logit econometric models. The analysis reveals several important findings. First, random forests predict Bitcoin and gold price directions with a higher degree of accuracy than logit models. Prediction accuracy for bagging and random forests is between 75% and 80% for a five-day prediction. For 10-day to 20-day forecasts bagging and random forests record accuracies greater than 85%. Second, technical indicators are the most important features for predicting Bitcoin and gold price direction, suggesting some degree of market inefficiency. Third, oil price volatility is important for predicting Bitcoin and gold prices indicating that Bitcoin is a substitute for gold in diversifying this type of volatility. By comparison, gold prices are more influenced by inflation than Bitcoin prices, indicating that gold can be used as a hedge or diversification asset against inflation.
Gyeongho Kim, Dong-Hyun Shin, Jae Gyeong Choi, Sunghoon Lim
Cryptocurrency has recently attracted substantial interest from investors due to its underlying philosophy of decentralization and transparency. Considering cryptocurrency’s volatility and unique characteristics, accurate price prediction is essential for developing successful investment strategies. To this end, the authors of this work propose a novel framework that predicts the price of Bitcoin (BTC), a dominant cryptocurrency. For stable prediction performance in unseen price range, the change point detection technique is employed. In particular, it is used to segment time-series data so that normalization can be separately conducted based on segmentation. In addition, on-chain data, the unique records listed on the blockchain that are inherent in cryptocurrencies, are collected and utilized as input variables to predict prices. Furthermore, this work proposes self-attention-based multiple long short-term memory (SAM-LSTM), which consists of multiple LSTM modules for on-chain variable groups and the attention mechanism, for the prediction model. Experiments with real-world BTC price data and various method setups have proven the proposed framework’s effectiveness in BTC price prediction. The results are promising, with the highest MAE, RMSE, MSE, and MAPE values of 0.3462, 0.5035, 0.2536, and 1.3251, respectively.
Naila Aslam, Furqan Rustam, Ernesto Lee, Patrick Bernard Washington · 5 authors
The cryptocurrency market has been developed at an unprecedented speed over the past few years. Cryptocurrency works similar to standard currency, however, virtual payments are made for goods and services without the intervention of any central authority. Although cryptocurrency ensures legitimate and unique transactions by utilizing cryptographic methods, this industry is still in its inception and serious concerns have been raised about its use. Analysis of the sentiments about cryptocurrency is highly desirable to provide a holistic view of peoples’ perceptions. In this regard, this study performs both sentiment analysis and emotion detection using the tweets related to the cryptocurrency which are widely used for predicting the market prices of cryptocurrency. For increasing the efficacy of the analysis, a deep learning ensemble model LSTM-GRU is proposed that combines two recurrent neural networks applications including long short term memory (LSTM) and gated recurrent unit (GRU). LSTM and GRU are stacked where the GRU is trained on the features extracted by LSTM. Utilizing term frequency-inverse document frequency, word2vec, and bag of words (BoW) features, several machine learning and deep learning approaches and a proposed ensemble model are investigated. Furthermore, TextBlob and Text2Emotion are studied for emotion analysis with the selected models. Comparatively, a larger number of people feel happy with the use of cryptocurrency, followed by fear and surprise emotions. Results suggest that the performance of machine learning models is comparatively better when BoW features are used. The proposed LSTM-GRU ensemble shows an accuracy of 0.99 for sentiment analysis, and 0.92 for emotion prediction and outperforms both machine learning and state-of-the-art models.
Sanal Kripto Para kavramı Bitcoin ile birlikte 2009 yılında dikkat çekmeye başlamış ve özellikle 2013 yılındaki fiyat artışı ile popülaritesi artmıştır. Sanal Kripto Para birimlerinin ilki ve öncüsü olan Bitcoin ile 2. En büyük piyasa değerine sahip olan Ethereum tasarımsal yapıları ve amaçları bakımından birbirlerinden oldukça farklıdır. Sanal bir para birimi olması için tasarlanan Bitcoin ile üzerinde akıllı kontratlar çalışmasına olanak vermek için tasarlanan Ethereum birçok alanda olduğu gibi iktisat alanında da oldukça dikkat çekmiş ve literatürde birçok çalışmaya konu olmuştur. Bu çalışmanın amacı Türkiye GSYH’sı, M2 Tanımı ile para arzı ve tüketici güven endeksinin Bitcoin ve Ethereum fiyatına olan etkilerini karşılaştırmalı olarak tahmin etmektir. Bu amaçla, Bitcoin ve Etherum’un Türk Lirası cinsinden fiyatlarını bağımlı değişken alan iki farklı model kurulmuştur. Kurulan modeller, Ocak 2016 ile Aralık 2020 dönemini kapsayan aylık veriler kullanılarak, zaman serisi analizi kapsamında, Johansen Eşbütünleşme Testi ve Tam Uyarlanmış En Küçük Kareler Yöntemi (FMOLS) kullanılarak uzun dönemde sınanmıştır. Yapılan analizin sonucunda hem Bitcoin hem de Ethereum’un Türk lirası cinsinden fiyatları, GSYH ve tüketici güven endeksi ile pozitif ilişkili, M2 para arzı ile negatif ilişkili bulunmuştur. Çalışmanın bulgularından bir diğeri ise toplam piyasa değeri Bitcoin’e göre daha düşük olan Ethereum’un tüm değişkenlerden daha çok etkilendiğidir. Elde edilen sonuçlar bu çalışmanın türetildiği Yüksek Lisans Tezindeki bulgular ile örtüşmekte ve birbirini desteklemektedir.
This paper provides a review of the Fractal Market Hypothesis (FMH) focusing on financial times series analysis. In order to put the FMH into a broader perspective, the Random Walk and Efficient Market Hypotheses are considered together with the basic principles of fractal geometry. After exploring the historical developments associated with different financial hypotheses, an overview of the basic mathematical modelling is provided. The principal goal of this paper is to consider the intrinsic scaling properties that are characteristic for each hypothesis. In regard to the FMH, it is explained why a financial time series can be taken to be characterised by a 1/t1−1/γ scaling law, where γ>0 is the Lévy index, which is able to quantify the likelihood of extreme changes in price differences occurring (or otherwise). In this context, the paper explores how the Lévy index, coupled with other metrics, such as the Lyapunov Exponent and the Volatility, can be combined to provide long-term forecasts. Using these forecasts as a quantification for risk assessment, short-term price predictions are considered using a machine learning approach to evolve a nonlinear formula that simulates price values. A short case study is presented which reports on the use of this approach to forecast Bitcoin exchange rate values.
Bu çalışma 2011 yılından itibaren temel olarak “belirsizlik” ve “ekonomi” anahtar kelimelerini içeren tweetlerin baz alınarak oluşturulduğu Twitter Bazlı Belirsizlik Endeksinin, son yılların gözde yatırım araçlarından olan kripto paraların volatilitesine etkisini incelemeyi amaçlamaktadır. Piyasa değeri en yüksek, Binance, Bitcoin, Cardano, Ethereum, Ripple ve Tether kripto paralar 18/01/2018- 11/07/2021 dönemi için günlük verilerle ARCH-GARCH ailesi modelleri ile incelenmiştir. Çalışmada öncelikle ortalama denklemi oluşturulan modellerin ARCH-GARCH modellerine uygunluğu sınanmış ve incelenen dönemde Bitcoin ve Ethereum için ARCH etkisinin olmadığı ancak Binance, Cardano, Ripple ve Tether için volatilite modellerinin kullanımının uygun olduğu bulgusu elde edilmiştir. Binance için GARCH (1,1), Cardano için GARCH-M (1,1), Ripple için ARCH (2) modeli volatiliteyi en iyi yakalayan model olarak seçilmiştir. Twitter Bazlı Belirsizlik Endeksinin bu modellerin hepsinde istatistiki olarak anlamlı ve pozitif bir etkiye sahip olduğu tespit edilmiştir. Bu sonuçlara göre bir sosyal medya platformu olan Twitter’da yer alan belirsizlik ve ekonomi içerikli tweetlerin kripto varlıkların volatilitesini etkilediğini söylemek mümkündür.
Sanjib Kumar Nayak, Sarat Chandra Nayak, Subhranginee Das
Artificial neural networks (ANNs) are suitable procedures for predicting financial time series (FTS). Cryptocurrencies are good investment assets; therefore, the effective prediction of cryptocurrencies has become a trending area of research. Capturing inherent uncertainties associated with cryptocurrency FTS with conventional methods is difficult. Though ANNs are the better alternative, fixing the optimal parameters of ANNs is a tedious job. This article develops a hybrid ANN through Rao algorithm (RA + ANN) for the effective prediction of six popular cryptocurrencies such as Bitcoin, Litecoin, Ethereum, CMC 200, Tether, and Ripple. Six comparative models such as GA + ANN, PSO + ANN, MLP, SVM, LSE, and ARIMA are developed and trained in a similar way. All these models are evaluated through the mean absolute percentage of error (MAPE) and average relative variance (ARV) metrics. It is found that the proposed RA + ANN generated the lowest MAPE and ARV values, statistically different as compared with existing methods mentioned above, and hence can be recommended as a potential financial instrument for predicting cryptocurrencies.
Sarafatema Peerzade, Dnyaneshwari Wayal, Gauri Kale
The proposed project work is totally supported and easy yet effective strategy named as Martingale. An automatic system which only requires only some pre-coded instructions to execute trades on variety of market variables starting from asset price to trading volume. The strategy along with each cryptocurrency, the benchmark against which the algorithm is tested is that the market’s performance. Returns are compared with the buying and so multiplying the trade volume at each loss and different scenarios are analysed to work out the chance related to the buying compared with an algorithmic strategy. Results are going to be in love with the market’s actual trends and also with some alternate possible trends to check all market scenarios. An internet interface will accompany the presentation allowing the users to check the strategies by entering their parameters and instantly seeing the results
We execute a comparative analysis of machine learning models for the time-series forecasting of the sign of next-day cryptocurrency returns. We begin by compiling a proprietary dataset that encompasses a wide array of potential cryptocurrency valuation factors (price trends, liquidity, volatility, network, production, investor attention), subsequently identifying and evaluating the most significant factors. We apply eight machine learning models to the dataset, utilizing them as classifiers to predict the sign of next day price returns for the three largest cryptocurrencies by market capitalization: bitcoin, ethereum, and ripple. We show that the most significant valuation factors for cryptocurrency returns are price trend variables, seven and thirty-day reversal, to be specific. We conclude that support vector machines result in the most accurate classifications for all three cryptocurrencies. Additionally, we find that boosted models like AdaBoost and XGBoost have the poorest classification accuracy. At length, we construct a probability-based trading strategy that secures either a daily long or short position on one of the three examined cryptocurrencies. Ultimately, the strategy yields a Sharpe of 2.8 and a cumulative log return of 3.72. On average, the strategy’s log returns outperformed standalone investments in all three cryptocurrencies by a factor of 5.64, and Sharpe ratios more than threefold.
There is a growing interest in the activities of the crypto market by various stakeholders. These stakeholders generally include investors, entrepreneurs, governments, fund managers, climate activists, institutional managers, employees with surplus funds, and crypto miners. This study aims to investigate the accuracy of the GARCH models for measuring and estimating Value-at-risk (VaR) using the Cryptocurrency index for future investment and managerial decision making. Because of this, the present study uses the top 30 Cryptocurrencies index in terms of Market capitalization excluding stable coins to determine the best GARCH models. Many entrepreneurs, institutional managers, fund managers, and other stakeholders have recently included cryptocurrency in their investment portfolio because of the increase in transactions and high returns growth in the global financial market with its associated high returns and volatility. Information communication technology has paved the way for such activities in the global markets. The daily data frequency was applied because of the availability of the data. The empirical analysis has been carried out for the period from January 2017 to December 2020 for a total of 1461observation. The returns volatility is estimated using SGARCH and EGARCH models. The findings evidenced that, using both normal distribution and Student t distribution, EGARCH provides a better measure and estimate than SGARCH concerning high persistence and volatility. Against this background, the present study also examined Backtesting to estimate Value at Risk. Interestingly, the findings of the available study would provide industry players, practitioners, entrepreneurs, and investors the maximum edge on how to use or measure such variables against others to make investment decisions. Also, the findings would subsequently contribute more insight into academia on the study area.